Adapting to the stream: an instance-attention GNN method for irregular multivariate time series data

Kun Han; Abigail M. Y. Koay; Ryan K. L. Ko; Weitong Chen; Miao Xu

doi:10.1007/s11704-024-40449-z

Back

Adapting to the stream: an instance-attention GNN method for irregular multivariate time series data

Journal article

Open access

Peer reviewed

Adapting to the stream: an instance-attention GNN method for irregular multivariate time series data

Kun Han, Abigail M. Y. Koay, Ryan K. L. Ko, Weitong Chen and Miao Xu

Frontiers of Computer Science, Vol.19, pp.1-13

2025

DOI: https://doi.org/10.1007/s11704-024-40449-z

Files and links (1)

pdf

s11704-024-40449-z1.51 MBDownload View

Published VersionCC BY V4.0, Open Access

Abstract

multivariate time series

irregular multivariate time series

graph neural networks

Multivariate time series (MTS) data are vital for various applications, particularly in machine learning tasks. However, challenges such as sensor failures can result in irregular and misaligned data with missing values, thereby complicating their analysis. While recent advancements use graph neural networks (GNNs) to manage these Irregular Multivariate Time Series (IMTS) data, they generally require a reliable graph structure, either pre-existing or inferred from adequate data to properly capture node correlations. This poses a challenge in applications where IMTS data are often streamed and waiting for future data to estimate a suitable graph structure becomes impractical. To overcome this, we introduce a dynamic GNN model suited for streaming characteristics of IMTS data, incorporating an instance-attention mechanism that dynamically learns and updates graph edge weights for realtime analysis. We also tailor strategies for high-frequency and low-frequency data to enhance prediction accuracy. Empirical results on real-world datasets demonstrate the superiority of our proposed model in both classification and imputation tasks.

Details

Title: Adapting to the stream: an instance-attention GNN method for irregular multivariate time series data
Authors: Kun Han - The University of Queensland
Abigail M. Y. Koay - University of the Sunshine Coast, Queensland, School of Science, Technology and Engineering
Ryan K. L. Ko - The University of Queensland
Weitong Chen (Corresponding Author) - The University of Adelaide
Miao Xu (Corresponding Author) - The University of Queensland
Publication details: Frontiers of Computer Science, Vol.19, pp.1-13
Publisher: Gaodeng Jiaoyu Chubanshe, Higher Education Press
Date published: 2025
DOI: 10.1007/s11704-024-40449-z
ISSN: 2095-2236; 2095-2228
Copyright note: This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made.
Grants: Detecting Key Concepts from Low-Quality Data for Better Decision, DE230101116, Australian Research Council (Australia, Canberra) - ARC
Advanced Data Analytics for Cost-effective Mushroom Cultivation, LP230200821, Australian Research Council (Australia, Canberra) - ARC
Future of Work: Achieving Efficiency and Productivity through Optimisation, IE240100275, Australian Research Council (Australia, Canberra) - ARC
Towards knowledge discovery from imperfect and evolving data, DP240103070, Australian Research Council (Australia, Canberra) - ARC
Grant note: We extend our sincere gratitude to UQ Cyber for their strategic funding, which has provided a PhD scholarship and access to essential equipment. The research work was also supported by the UoA Startup Grant, UQ Cyber Security Seed Funding.
Organisation Unit: Healthy Ageing Research Cluster; School of Science, Technology and Engineering
Language: English
Record Identifier: 991103723402621
Output Type: Journal article

Metrics

92 File views/ downloads

20 Record Views

1 Times Cited - Web of Science

InCites Highlights

These are selected metrics from InCites Benchmarking & Analytics tool, related to this output

Collaboration types: Domestic collaboration
Web Of Science research areas: Computer Science, Information Systems; Computer Science, Software Engineering; Computer Science, Theory & Methods